© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 33080
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ccas
    -0.89
    实施
    -0.85
     nalazi
    -0.82
    valis
    -0.80
     xadrez
    -0.77
    ه‌
    -0.77
     piemē
    -0.77
    ᄎ
    -0.77
    colazione
    -0.76
    curities
    -0.76
    POSITIVE LOGITS
     Mensch
    0.84
    eció
    0.82
    varande
    0.77
    பெ
    0.76
    Lori
    0.75
    siert
    0.73
    Lst
    0.73
     hardships
    0.72
     Ditto
    0.71
     headboard
    0.71
    Activations Density 0.133%

    No Known Activations